Pro@programming.dev to Programming@programming.devEnglish · 8 days agoSurprisingly Fast AI-Generated Kernels We Didn’t Mean to Publish (Yet)crfm.stanford.eduexternal-linkmessage-square5fedilinkarrow-up123arrow-down16cross-posted to: [email protected]
arrow-up117arrow-down1external-linkSurprisingly Fast AI-Generated Kernels We Didn’t Mean to Publish (Yet)crfm.stanford.eduPro@programming.dev to Programming@programming.devEnglish · 8 days agomessage-square5fedilinkcross-posted to: [email protected]
minus-squareonlinepersona@programming.devlinkfedilinkarrow-up1·6 days agoThe weights for the neural network or the embeddings? Anti Commercial-AI license
minus-squarebitfucker@programming.devlinkfedilinkarrow-up3·6 days agoNo. Normally the kernel doesn’t get updated in the network during training. They are called hyper-parameters. They do affect training, but they are not updated by the training algorithm
The weights for the neural network or the embeddings?
Anti Commercial-AI license
No. Normally the kernel doesn’t get updated in the network during training. They are called hyper-parameters. They do affect training, but they are not updated by the training algorithm